Turn Image Generation Prompt into a reviewable shot contract.

Create a 15 sec 16:9 video direction for “image generation prompt” in the context of general video prompts.
Subject and action: Show the subject entering the setting, performing one clear action, and reaching a visible end state across three connected beats.
Camera and edit: Begin with a restrained wide establishing frame, move to a medium action shot, and finish on one legible detail.
Continuity: Preserve subject identity, wardrobe, hero-object details, geography, lighting direction, and direction of travel across every shot.
Sound: Use original location ambience, tactile action sounds, and no copyrighted music.
Production focus: Make general video prompts workflow and Image Generation Prompt learning visible through the scene rather than explaining it with text overlays.
Delivery: 16:9, 15 sec, text-led; realistic motion and material behavior; no logos, fake interface, duplicated subjects, impossible physics, or unsupported result claims.

Create a 12 sec 9:16 video direction for “image generation prompt” in the context of general video prompts.
Subject and action: Communicate the premise in the first beat, demonstrate one change in the middle, and hold the result long enough to read.
Camera and edit: Use an immediate close opening, two readable handheld reframes, and a stable final composition designed for a vertical crop.
Continuity: Preserve subject identity, wardrobe, hero-object details, geography, lighting direction, and direction of travel across every shot.
Sound: Keep speech original and concise; connect cuts with room tone and motivated practical sounds.
Production focus: Make general video prompts workflow and Image Generation Prompt learning visible through the scene rather than explaining it with text overlays.
Delivery: 9:16, 12 sec, text-led; realistic motion and material behavior; no logos, fake interface, duplicated subjects, impossible physics, or unsupported result claims.

Create a 18 sec 16:9 video direction for “image generation prompt” in the context of general video prompts.
Subject and action: Introduce the referenced subject, show one physically plausible interaction, and return to a composition that can be checked against the source.
Camera and edit: Use the supplied reference as the identity, material, palette, and proportion constraint; cover it with wide, medium, and detail views.
Continuity: Preserve subject identity, wardrobe, hero-object details, geography, lighting direction, and direction of travel across every shot.
Sound: Use grounded ambience and synchronized object sounds; do not imply audio that is not established by the scene.
Production focus: Make general video prompts workflow and Image Generation Prompt learning visible through the scene rather than explaining it with text overlays.
Delivery: 16:9, 18 sec, reference-led; realistic motion and material behavior; no logos, fake interface, duplicated subjects, impossible physics, or unsupported result claims.

Create a 20 sec 4:3 video direction for “image generation prompt” in the context of general video prompts.
Subject and action: Repeat one subject, one hero object, and one spatial relationship through setup, action, reaction, and resolved end frame.
Camera and edit: Stage four connected shots with consistent screen direction, eyelines, lens logic, and motivated camera movement.
Continuity: Preserve subject identity, wardrobe, hero-object details, geography, lighting direction, and direction of travel across every shot.
Sound: Carry one continuous ambient bed across edits and add only original, scene-motivated effects.
Production focus: Make general video prompts workflow and Image Generation Prompt learning visible through the scene rather than explaining it with text overlays.
Delivery: 4:3, 20 sec, reference-led; realistic motion and material behavior; no logos, fake interface, duplicated subjects, impossible physics, or unsupported result claims.